4 papers · 1 filter
RASET: Router-Agnostic Safety-Critical Expert Tuning Exposes Localized Safety Enforcement Failures in Mixture-of-Experts LLMs
Zhibo Zhang, Yuxi Li, Zhen Ouyang +2
Mixture-of-Experts (MoE) LLMs rely on sparse, router-driven expert activation, yet how safety alignment interacts with routed expert specialization remains underexplored. A common…
Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation
Zhibo Zhang, Yuxi Li, Kailong Wang +3
Large Language Models (LLMs) have achieved remarkable success across domains such as healthcare, education, and cybersecurity. However, this openness also introduces significant se…
Detecting LLM Fact-conflicting Hallucinations Enhanced by Temporal-logic-based Reasoning
Ningke Li, Yahui Song, Kailong Wang +4
Large language models (LLMs) face the challenge of hallucinations -- outputs that seem coherent but are actually incorrect. A particularly damaging type is fact-conflicting halluci…
GlitchProber: Advancing Effective Detection and Mitigation of Glitch Tokens in Large Language Models
Zhibo Zhang, Wuxia Bai, Yuxi Li +6
Large language models (LLMs) have achieved unprecedented success in the field of natural language processing. However, the black-box nature of their internal mechanisms has brought…